SSL: Semi-Supervised Learning

Semi-supervised learning has attracted the attention of machine learning community because of its high accuracy with less annotating effort compared with supervised learning.The question that semi-supervised learning wants to address is: given a relatively small labeled dataset and a large unlabeled dataset, how to design classification algorithms learning from both ? This package is a collection of some classical semi-supervised learning algorithms in the last few decades.

Version: 0.1
Depends: R (≥ 3.2)
Imports: NetPreProc (≥ 1.1), Rcpp (≥ 0.12.2), caret (≥ 6.0-52), proxy (≥ 0.4-15), xgboost (≥ 0.4), klaR (≥ 0.6-12), e1071 (≥ 1.6-7), stats (≥ 3.2)
LinkingTo: Rcpp
Published: 2016-05-14
Author: Junxiang Wang
Maintainer: Junxiang Wang <xianggebenben at>
License: GPL (≥ 3)
NeedsCompilation: yes
CRAN checks: SSL results


Reference manual: SSL.pdf
Package source: SSL_0.1.tar.gz
Windows binaries: r-devel:, r-release:, r-oldrel:
OS X Mavericks binaries: r-release: SSL_0.1.tgz, r-oldrel: SSL_0.1.tgz


Please use the canonical form to link to this page.